100 lines
3.0 KiB
Python
100 lines
3.0 KiB
Python
#!/usr/bin/env python3
|
|
"""
|
|
翻译题目内容 - 使用翻译API
|
|
"""
|
|
import json
|
|
import os
|
|
import time
|
|
import urllib.request
|
|
import urllib.parse
|
|
import ssl
|
|
|
|
ssl_context = ssl.create_default_context()
|
|
ssl_context.check_hostname = False
|
|
ssl_context.verify_mode = ssl.CERT_NONE
|
|
|
|
def translate_text(text, target_lang='zh-CN'):
|
|
"""
|
|
使用Google Translate API翻译文本
|
|
"""
|
|
if not text or not text.strip():
|
|
return text
|
|
|
|
try:
|
|
base_url = "https://translate.googleapis.com/translate_a/single"
|
|
params = {
|
|
'client': 'gtx',
|
|
'sl': 'en',
|
|
'tl': target_lang,
|
|
'dt': 't',
|
|
'q': text
|
|
}
|
|
|
|
url = base_url + '?' + urllib.parse.urlencode(params)
|
|
|
|
req = urllib.request.Request(url)
|
|
req.add_header('User-Agent', 'Mozilla/5.0')
|
|
|
|
with urllib.request.urlopen(req, context=ssl_context, timeout=30) as response:
|
|
result = json.loads(response.read().decode('utf-8'))
|
|
|
|
if result and result[0]:
|
|
translated = ''.join([item[0] for item in result[0] if item[0]])
|
|
return translated
|
|
except Exception as e:
|
|
print(f"翻译错误: {e}")
|
|
return text
|
|
|
|
return text
|
|
|
|
def translate_questions(input_file, output_file, start_index=0, batch_size=50):
|
|
"""
|
|
翻译题目，支持分批处理
|
|
"""
|
|
with open(input_file, 'r', encoding='utf-8') as f:
|
|
questions = json.load(f)
|
|
|
|
total = len(questions)
|
|
end_index = min(start_index + batch_size, total)
|
|
|
|
print(f"正在翻译第 {start_index + 1} 到 {end_index} 题，共 {total} 题")
|
|
|
|
for i in range(start_index, end_index):
|
|
q = questions[i]
|
|
print(f"翻译 Topic {q['topic']} - Question {q['question_num']} ({i+1}/{total})")
|
|
|
|
if 'stem_cn' not in q or not q['stem_cn']:
|
|
q['stem_cn'] = translate_text(q['stem'])
|
|
time.sleep(0.5)
|
|
|
|
for opt in q['options']:
|
|
if 'text_cn' not in opt or not opt['text_cn']:
|
|
opt['text_cn'] = translate_text(opt['text'])
|
|
time.sleep(0.3)
|
|
|
|
with open(output_file, 'w', encoding='utf-8') as f:
|
|
json.dump(questions, f, ensure_ascii=False, indent=2)
|
|
|
|
print(f"翻译进度: {end_index}/{total}")
|
|
|
|
if end_index < total:
|
|
print(f"继续翻译请运行: python3 translate_api.py --start {end_index}")
|
|
|
|
return questions
|
|
|
|
if __name__ == '__main__':
|
|
import argparse
|
|
|
|
parser = argparse.ArgumentParser()
|
|
parser.add_argument('--start', type=int, default=0, help='起始索引')
|
|
parser.add_argument('--batch', type=int, default=50, help='批量大小')
|
|
args = parser.parse_args()
|
|
|
|
input_file = '/Users/duguoyou/D365/exam_data/questions.json'
|
|
output_file = '/Users/duguoyou/D365/exam_data/questions_translated.json'
|
|
|
|
if os.path.exists(output_file):
|
|
input_file = output_file
|
|
|
|
translate_questions(input_file, output_file, args.start, args.batch)
|